English

MIDI-Draw: Sketching to Control Melody Generation

Sound 2023-05-22 v1 Artificial Intelligence Machine Learning Audio and Speech Processing

Abstract

We describe a proof-of-principle implementation of a system for drawing melodies that abstracts away from a note-level input representation via melodic contours. The aim is to allow users to express their musical intentions without requiring prior knowledge of how notes fit together melodiously. Current approaches to controllable melody generation often require users to choose parameters that are static across a whole sequence, via buttons or sliders. In contrast, our method allows users to quickly specify how parameters should change over time by drawing a contour.

Keywords

Cite

@article{arxiv.2305.11605,
  title  = {MIDI-Draw: Sketching to Control Melody Generation},
  author = {Tashi Namgyal and Peter Flach and Raul Santos-Rodriguez},
  journal= {arXiv preprint arXiv:2305.11605},
  year   = {2023}
}

Comments

Late-Breaking / Demo Session Extended Abstract, ISMIR 2022 Conference

R2 v1 2026-06-28T10:39:09.015Z